Machine learning
Dispatches from the ULMFiT trenches
Don’t just look at the benchmark figures when you evaluate your language model. A subjective judgement can also lead to interesting insights.
Why ULMFiT can still matter: training and inference times
In real-life applications computational efficiency of ML models is as important as evaluation metrics
Resurrecting monolingual recurrent language models with ULMFiT for Tensorflow
Recurrent language models are still alive and kicking. We release pretrained Polish and English ULMFiT models for Tensorflow Hub.
Superskalarny Doradca: W jaki sposób myśleć o rekomendacjach
Marketing Machine to zbiorcza nazwa (nasz trademark) dla algorytmów rekomendacyjnych, które udostępniamy klientom edrone. Polegają one na różnych (niejednokrotnie najprostszych, ale wciąż skutecznych) technikach sprzedażowych zaadaptowanych przez sztuczną inteligencję.
Continual Learning
Continual learning is a machine learning domain that aims to mitigate catastrophic forgetting and enable models to be trained with an incoming stream of training data.
From research to production and back: Machine Learning with AWS
Let's see how Machine Learning can be built in the cloud. We’ll explore AWS services that will help you boost your productivity on the path from research to production.
Concordância entre Anotadores: A Linguagem em Disputa
Quando o assunto é Processamento de Linguagem Natural e o desenvolvimento de assistentes por voz, mais cedo ou mais tarde você encontrará o termo "concordância entre anotadores". Este acordo é fundamental para atingirmos a ilusão de que as máquinas estão, de fato, entendendo palavras.
A Mente do Fantasma: Como as Recomendações são Definidas
Informações são essenciais para recomendar produtos corretamente. Assim que sabemos algo sobre um usuário, podemos confrontá-lo com um sistema de Inteligência Artificial e o Fantasma na Máquina de Vendas fará o resto.
